An index is provided that holds information about each image content item in a collection of items, For each image content item, a first information item identifying the image content item and its location on a network, and at least one of (i) a second information item identifying a signature value of an object in the image content, or (ii) identification of a recognized object in the image content.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method performed by a system of one or more computers for selecting image content, the method comprising: performing image analysis on a collection of image content items to obtain information about each image content item, including one or more of (i) identification of one or more objects in one or more image content items, and (ii) identification of a feature for each identified object; detecting content that is to be used for image selection; providing, to a user, one or more image selection results from the collection of image content items based on (i) the detected content and (ii) the information obtained from the image analysis; receiving, from the user, user-input associated with an user-interactable interface element associated with a first image selection result of the one or more image selection results, the user input specifying selection of a parameter indicated by the user-interactable interface element and referring to one or more properties of first image content of the first image selection result; and providing, to the user, one or more additional image selection results based on (i) the detected content, (ii) the information obtained from the image analysis, and (iii) the selected parameter associated with the first image selection result.
The system analyzes a collection of images, identifying objects and their features within each image. When a user provides content for image selection (e.g., text or an image), the system uses this content along with the image analysis results to find relevant images from the collection. The system presents these image selection results to the user. If the user interacts with an element related to a displayed image, selecting a specific parameter (e.g., by clicking a color in the image), the system refines the image selection results, now considering the initial content, the image analysis information, and the user-selected parameter to provide more relevant images.
2. The method of claim 1 , wherein: receiving the user input comprises causing a color picker user interface element to be displayed with the first image content and receiving, as a result of the user interacting with the color picker, a particular color; and providing the one or more additional image selection results comprises performing a search operation to identify one or more additional image content items containing color that matches the particular color.
Building upon the image selection method, when the user interacts with an image selection result, a color picker is displayed. The user selects a specific color using this picker. The system then searches for additional images in the collection that contain the selected color. This refines the search based on user-specified color properties within an initial image selection.
3. The method of claim 1 , wherein: receiving the user input comprises receiving, from the user, an identification of a key region within the first image content and determining one or more local features within the key region; and providing the one or more additional image selection results comprises performing a search operation using the local features.
Expanding on the core image selection method, user interaction involves selecting a key region within an image. The system determines local features within that selected region. Subsequent image searches then prioritize results that match these local features extracted from the user-defined key region, narrowing the search to visually similar areas in other images.
4. The method of claim 1 , wherein detecting content for image selection comprises: receiving a user image content item from the user for selection; identifying an object of the user image content item; and forming a criteria for providing the image selection results based on the identified object.
In this image selection method, the user provides an image for selection. The system identifies objects within the user's image and then forms criteria based on the identified objects. These criteria are then used to provide image selection results that are relevant to the objects found in the user's input image. For example, if the user uploads a picture of a "dog," the system will use "dog" as a search criteria.
5. The method of claim 4 , wherein forming the criteria includes forming a text string criteria that is based on identification of the object.
Expanding on the previous method where an object is identified from a user-provided image, the system creates a text string based on this object's identification. This text string then becomes the search query. For example, if the identified object is a "red apple", the system forms the text string "red apple" as the search criteria.
6. The method of claim 1 , wherein detecting content for image selection comprises: receiving a user text content for selecting image content items from the user; and forming a criteria for providing the image selection results based on the text content.
This image selection method allows users to input text. The system uses this text to form criteria and provides image selection results based on that criteria. The user enters "sunset over ocean," and the system finds images matching "sunset over ocean".
7. The method of claim 1 , wherein detecting content for image selection comprises: receiving a user image content item from the user for selection; identifying text data associated with the image content item; and forming a criteria for providing the image selection results based on the text data associated with the image content item.
In this variation, the user provides an image, and the system identifies any text data associated with it. The system then uses this text data to form the criteria for providing image selection results. For example, if the uploaded image contains the text "Summer Sale", the system will use that as the search term.
8. The method of claim 1 , wherein detecting content for image selection comprises receiving an identifier of image content of a particular merchandise object, and wherein providing the image selection results comprises providing image selection results of different image content items of different merchandise objects based on a determination that the different image content items are similar to the particular merchandise object.
This selection method begins with an identifier related to image content of a product. The system finds image content of other merchandise objects that are determined to be similar to the original product. For instance, using an identifier of a "Nike shoe" image, the system would find similar "running shoe" images from other brands.
9. The method of claim 1 , further comprising providing a link with each of the different image content items of different merchandise objects, wherein the link is selectable to enable the user to purchase the merchandise objects from a network site operated by a merchant.
Expanding on the image search functionality, this system also includes links alongside image results of different merchandise objects, which allows the user to purchase the merchandise objects directly from a merchant's online store. For example, each displayed running shoe image from the previous search contains a link to purchase it from that specific brand.
10. A system comprising: a computing device; and a computer-readable medium coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations comprising performing image analysis on a collection of image content items to obtain information about each image content item, including one or more of (i) identification of one or more objects in one or more image content items, and (ii) identification of a feature for each identified object; detecting content that is to be used for image selection; providing, to a user, one or more image selection results from the collection of image content items based on (i) the detected content and (ii) the information obtained from the image analysis; receiving, from the user, user-input associated with an user-interactable interface element associated with a first image selection result of the one or more image selection results, the user input specifying selection of a parameter indicated by the user-interactable interface element and referring to one or more properties of first image content of the first image selection result; and providing, to the user, one or more additional image selection results based on (i) the detected content, (ii) the information obtained from the image analysis, and (iii) the selected parameter associated with the first image selection result.
The system analyzes a collection of images, identifying objects and their features within each image. When a user provides content for image selection (e.g., text or an image), the system uses this content along with the image analysis results to find relevant images from the collection. The system presents these image selection results to the user. If the user interacts with an element related to a displayed image, selecting a specific parameter (e.g., by clicking a color in the image), the system refines the image selection results, now considering the initial content, the image analysis information, and the user-selected parameter to provide more relevant images.
11. The system of claim 10 , wherein: receiving the user input comprises causing a color picker user interface element to be displayed with the first image content and receiving, as a result of the user interacting with the color picker, a particular color; and providing the one or more additional image selection results comprises performing a search operation to identify one or more additional image content items containing color that matches the particular color.
Building upon the image selection system, when the user interacts with an image selection result, a color picker is displayed. The user selects a specific color using this picker. The system then searches for additional images in the collection that contain the selected color. This refines the search based on user-specified color properties within an initial image selection.
12. The system of claim 10 , wherein: receiving the user input comprises receiving, from the user, an identification of a key region within the first image content and determining one or more local features within the key region; and providing the one or more additional image selection results comprises performing a search operation using the local features.
Expanding on the core image selection system, user interaction involves selecting a key region within an image. The system determines local features within that selected region. Subsequent image searches then prioritize results that match these local features extracted from the user-defined key region, narrowing the search to visually similar areas in other images.
13. The system of claim 10 , wherein detecting content for image selection comprises: receiving a user image content item from the user for selection; identifying an object of the user image content item; and forming a criteria for providing the image selection results based on the identified object.
In this image selection system, the user provides an image for selection. The system identifies objects within the user's image and then forms criteria based on the identified objects. These criteria are then used to provide image selection results that are relevant to the objects found in the user's input image. For example, if the user uploads a picture of a "dog," the system will use "dog" as a search criteria.
14. The system of claim 13 , wherein forming the criteria includes forming a text string criteria that is based on identification of the object.
Expanding on the previous system where an object is identified from a user-provided image, the system creates a text string based on this object's identification. This text string then becomes the search query. For example, if the identified object is a "red apple", the system forms the text string "red apple" as the search criteria.
15. The system of claim 10 , wherein detecting content for image selection comprises receiving an identifier of image content of a particular merchandise object, and wherein providing the image selection results comprises providing image selection results of different image content items of different merchandise objects based on a determination that the different image content items are similar to the particular merchandise object.
This selection system begins with an identifier related to image content of a product. The system finds image content of other merchandise objects that are determined to be similar to the original product. For instance, using an identifier of a "Nike shoe" image, the system would find similar "running shoe" images from other brands.
16. Non-transitory computer storage media encoded with one or more computer programs, the one or more computer programs comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising: performing image analysis on a collection of image content items to obtain information about each image content item, including one or more of (i) identification of one or more objects in one or more image content items, and (ii) identification of a feature for each identified object; detecting content that is to be used for image selection; providing, to a user, one or more image selection results from the collection of image content items based on (i) the detected content and (ii) the information obtained from the image analysis; receiving, from the user, user-input associated with an user-interactable interface element associated with a first image selection result of the one or more image selection results, the user input specifying selection of a parameter indicated by the user-interactable interface element and referring to one or more properties of first image content of the first image selection result; and providing, to the user, one or more additional image selection results based on (i) the detected content, (ii) the information obtained from the image analysis, and (iii) the selected parameter associated with the first image selection result.
A non-transitory computer storage medium stores instructions that cause a computer to analyze a collection of images, identifying objects and their features within each image. When a user provides content for image selection (e.g., text or an image), the computer uses this content along with the image analysis results to find relevant images from the collection. The computer presents these image selection results to the user. If the user interacts with an element related to a displayed image, selecting a specific parameter (e.g., by clicking a color in the image), the computer refines the image selection results, now considering the initial content, the image analysis information, and the user-selected parameter to provide more relevant images.
17. The non-transitory computer storage media of claim 16 , wherein: receiving the user input comprises causing a color picker user interface element to be displayed with the first image content and receiving, as a result of the user interacting with the color picker, a particular color; and providing the one or more additional image selection results comprises performing a search operation to identify one or more additional image content items containing color that matches the particular color.
Building upon the image selection method stored on the computer storage medium, when the user interacts with an image selection result, a color picker is displayed. The user selects a specific color using this picker. The computer then searches for additional images in the collection that contain the selected color. This refines the search based on user-specified color properties within an initial image selection.
18. The non-transitory computer storage media of claim 16 , wherein: receiving the user input comprises receiving, from the user, an identification of a key region within the first image content and determining one or more local features within the key region; and providing the one or more additional image selection results comprises performing a search operation using the local features.
Expanding on the core image selection method stored on the computer storage medium, user interaction involves selecting a key region within an image. The computer determines local features within that selected region. Subsequent image searches then prioritize results that match these local features extracted from the user-defined key region, narrowing the search to visually similar areas in other images.
19. The non-transitory computer storage media of claim 16 , wherein detecting content for image selection comprises: receiving a user image content item from the user for selection; identifying an object of the user image content item; and forming a criteria for providing the image selection results based on the identified object.
In this image selection method stored on the computer storage medium, the user provides an image for selection. The computer identifies objects within the user's image and then forms criteria based on the identified objects. These criteria are then used to provide image selection results that are relevant to the objects found in the user's input image. For example, if the user uploads a picture of a "dog," the computer will use "dog" as a search criteria.
20. The non-transitory computer storage media of claim 16 , wherein forming the criteria includes forming a text string criteria that is based on identification of the object.
Expanding on the previous method stored on the computer storage medium where an object is identified from a user-provided image, the computer creates a text string based on this object's identification. This text string then becomes the search query. For example, if the identified object is a "red apple", the computer forms the text string "red apple" as the search criteria.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
April 10, 2015
June 13, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.